Showing 2025Show all
2 papers · 1 filter
cs.LG2025
Near Optimal Best Arm Identification for Clustered Bandits
Yash, Nikhil Karamchandani, Avishek Ghosh
This work investigates the problem of best arm identification for multi-agent multi-armed bandits. We consider agents grouped into clusters, where each cluster solves a sto…
cs.GT2025
Incentivize Contribution and Learn Parameters Too: Federated Learning with Strategic Data Owners
Drashthi Doshi, Aditya Vema Reddy Kesari, Avishek Ghosh +2
In federated learning (FL), a center trains a shared model from updates that clients compute on their private data. Collecting and training on data is costly, so a strategic client…